Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1386 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5149. Min Range: -2.5149

Max Act: 2.5149. Min Act: -0.0000

Data Index: 1408828 (Python Code)

Max Activating Token Index: 987

Text #1

Max Range: 2.5149. Min Range: -2.5149

Max Act: 2.3393. Min Act: -0.0000

Data Index: 919804 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 2.5149. Min Range: -2.5149

Max Act: 2.1203. Min Act: -0.0000

Data Index: 1053316 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 2.5149. Min Range: -2.5149

Max Act: 2.1163. Min Act: -0.0000

Data Index: 1159711 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 2.5149. Min Range: -2.5149

Max Act: 2.0972. Min Act: -0.0000

Data Index: 889361 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 2.5149. Min Range: -2.5149

Max Act: 2.0970. Min Act: -0.0000

Data Index: 147673 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 2.5149. Min Range: -2.5149

Max Act: 2.2922. Min Act: -0.0000

Data Index: 1101243 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 2.5149. Min Range: -2.5149

Max Act: 1.9919. Min Act: -0.0000

Data Index: 432461 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 2.5149. Min Range: -2.5149

Max Act: 2.0992. Min Act: -0.0000

Data Index: 309547 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 2.5149. Min Range: -2.5149

Max Act: 1.9340. Min Act: -0.0000

Data Index: 1194108 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 2.5149. Min Range: -2.5149

Max Act: 1.8242. Min Act: -0.0000

Data Index: 808061 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 2.5149. Min Range: -2.5149

Max Act: 1.9103. Min Act: -0.0000

Data Index: 755338 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 2.5149. Min Range: -2.5149

Max Act: 1.8879. Min Act: -0.0000

Data Index: 259263 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 2.5149. Min Range: -2.5149

Max Act: 1.7980. Min Act: -0.0000

Data Index: 758103 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 2.5149. Min Range: -2.5149

Max Act: 1.8560. Min Act: -0.0000

Data Index: 1016905 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 2.5149. Min Range: -2.5149

Max Act: 1.7549. Min Act: -0.0000

Data Index: 1244551 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 2.5149. Min Range: -2.5149

Max Act: 1.8592. Min Act: -0.0000

Data Index: 214101 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 2.5149. Min Range: -2.5149

Max Act: 1.7253. Min Act: -0.0000

Data Index: 490862 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 2.5149. Min Range: -2.5149

Max Act: 1.7967. Min Act: -0.0000

Data Index: 60980 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 2.5149. Min Range: -2.5149

Max Act: 1.8013. Min Act: -0.0000

Data Index: 911339 (C4 (Web Text))

Max Activating Token Index: 129